Public Transit Arrival Prediction: a Seq2Seq RNN Approach

@article{Bhutani2022PublicTA,
  title={Public Transit Arrival Prediction: a Seq2Seq RNN Approach},
  author={Nancy Bhutani and Soumen Pachal and Avinash Achar},
  journal={ArXiv},
  year={2022},
  volume={abs/2210.01655}
}
—Arrival/Travel times for public transit exhibit vari- ability on account of factors like seasonality, dwell times at bus stops, traffic signals, travel demand fluctuation etc. The devel- oping world in particular is plagued by additional factors like lack of lane discipline, excess vehicles, diverse modes of transport and so on. This renders the bus arrival time prediction (BATP) to be a challenging problem especially in the developing world. A novel data-driven model based on recurrent neural… 

Figures and Tables from this paper

References

SHOWING 1-10 OF 46 REFERENCES

Dynamic Bus Arrival Time Prediction: A temporal difference learning approach

The central idea of the method is to recast the dynamic prediction problem as a value-function prediction problem under a suitably constructed Markov reward process (MRP) and explore a family of value- function predictors using temporal-difference (TD) learning for bus prediction.

Dynamic Bus Arrival Time Prediction exploiting Non-linear Correlations

The current work proposes a data-driven method to perform bus arrival time prediction in real-time using an Extended Kalman Filter (EKF) to solve the real time prediction problem on an associated non-linear dynamical system (NLDS) model.

Multi-output bus travel time prediction with convolutional LSTM neural network

BusTr: Predicting Bus Travel Times from Real-Time Traffic

BusTr, a machine-learned model for translating road traffic forecasts into predictions of bus delays used by Google Maps, is presented, demonstrating that the neural sequence model improves over DeepTTE, the state-of-the-art baseline, both in performance and training stability.

Towards Attention-Based Convolutional Long Short-Term Memory for Travel Time Prediction of Bus Journeys

A convolutional long short-term memory (ConvLSTM) model with a self-attention mechanism that accurately predicts the running time of each segment of the trips and the waiting time at each station and is more robust to capture long-range dependence in time series data as well.

To each route its own ETA: A generative modeling framework for ETA prediction

  • CharulP. Biyani
  • Computer Science
    2019 IEEE Intelligent Transportation Systems Conference (ITSC)
  • 2019
This work presents a simple but robust model for ETA estimation for a bus route that only relies on the historical data of the particular route and proposes a system that generates ETA information for a trip and updates it as the trip progresses based on the real-time information.

Bus travel time prediction: a log-normal auto-regressive (AR) modelling approach

This study proposes two predictive modelling methodologies using the concepts of time series analysis, namely (a) classical seasonal AR model with possible integrating non-stationary effects and (b) linear non- stationary AR approach, a novel technique exploiting the notion of partial correlation for learning from data to predict arrival time of buses efficiently.

Bus Arrival Time Modeling Based on Auckland Data

Research results indicated that time series models outperformed regression techniques, with the time series artificial neural network being the most successful of the seven models developed.

Performance Comparison of Bus Travel Time Prediction Models across Indian Cities

This work aims at developing a reliable structure for predicting arrival/travel time of various public transport systems under heterogeneous traffic conditions existing in India.

Dynamic Travel Time Prediction Models for Buses Using Only GPS Data